Neural network approach to prediction of the liquid petroleum products viscosity

An approach to predicting the viscosity and density of petroleum products using artificial neural networks was proposed. Based on reliable data on the thermophysical properties, viscosity and density of petroleum products, models of multi-layer neural networks with a different number of hidden layer...

Ամբողջական նկարագրություն

Պահպանված է:

Մատենագիտական մանրամասներ
Հիմնական հեղինակներ:	Koldaev, A. I., Колдаев, А. И.
Այլ հեղինակներ:	Boldyrev, D. V.
Ձևաչափ:	Статья
Լեզու:	English
Հրապարակվել է:	Institute of Electrical and Electronics Engineers Inc. 2021
Խորագրեր:	Artificial neural network Petroleum products Prediction of the densityf Prediction of the viscosity Bayesian networks Multilayer neural networks
Առցանց հասանելիություն:	https://dspace.ncfu.ru/handle/20.500.12258/14711
Ցուցիչներ:	Ավելացրեք ցուցիչ Չկան պիտակներ, Եղեք առաջինը, ով նշում է այս գրառումը!

id	ir-20.500.12258-14711
record_format	dspace
spelling	ir-20.500.12258-147112021-01-18T12:55:06Z Neural network approach to prediction of the liquid petroleum products viscosity Koldaev, A. I. Колдаев, А. И. Boldyrev, D. V. Болдырев, Д. В. Artificial neural network Petroleum products Prediction of the densityf Prediction of the viscosity Bayesian networks Multilayer neural networks An approach to predicting the viscosity and density of petroleum products using artificial neural networks was proposed. Based on reliable data on the thermophysical properties, viscosity and density of petroleum products, models of multi-layer neural networks with a different number of hidden layers were developed, which were trained on an array of experimental data using the Levenberg-Marquardt and Bayesian regularization algorithms. The test results showed that models of neural networks trained by the Levenberg-Marquardt algorithm are unable to predict the viscosity with sufficient accuracy for practical purposes for those values of input signals that were not involved in their training. The best predictive capabilities in terms of the ratio of accuracy and computational costs were provided by neural networks with three hidden layers, trained by the Bayesian regularization algorithm, for which the average relative deviation of the calculated deviations from the experimental data was 0.8% 2021-01-18T12:48:18Z 2021-01-18T12:48:18Z 2020 Статья Grigoriev, B.A., Koldaev, A.I., Boldyrev, D.V. Neural network approach to prediction of the liquid petroleum products viscosity // 2020 International Multi-Conference on Industrial Engineering and Modern Technologies, FarEastCon 2020. - 2020. - Номер статьи 9271453 http://hdl.handle.net/20.500.12258/14711 en 2020 International Multi-Conference on Industrial Engineering and Modern Technologies, FarEastCon 2020 application/pdf Institute of Electrical and Electronics Engineers Inc.
institution	СКФУ
collection	Репозиторий
language	English
topic	Artificial neural network Petroleum products Prediction of the densityf Prediction of the viscosity Bayesian networks Multilayer neural networks
spellingShingle	Artificial neural network Petroleum products Prediction of the densityf Prediction of the viscosity Bayesian networks Multilayer neural networks Koldaev, A. I. Колдаев, А. И. Neural network approach to prediction of the liquid petroleum products viscosity
description	An approach to predicting the viscosity and density of petroleum products using artificial neural networks was proposed. Based on reliable data on the thermophysical properties, viscosity and density of petroleum products, models of multi-layer neural networks with a different number of hidden layers were developed, which were trained on an array of experimental data using the Levenberg-Marquardt and Bayesian regularization algorithms. The test results showed that models of neural networks trained by the Levenberg-Marquardt algorithm are unable to predict the viscosity with sufficient accuracy for practical purposes for those values of input signals that were not involved in their training. The best predictive capabilities in terms of the ratio of accuracy and computational costs were provided by neural networks with three hidden layers, trained by the Bayesian regularization algorithm, for which the average relative deviation of the calculated deviations from the experimental data was 0.8%
author2	Boldyrev, D. V.
author_facet	Boldyrev, D. V. Koldaev, A. I. Колдаев, А. И.
format	Статья
author	Koldaev, A. I. Колдаев, А. И.
author_sort	Koldaev, A. I.
title	Neural network approach to prediction of the liquid petroleum products viscosity
title_short	Neural network approach to prediction of the liquid petroleum products viscosity
title_full	Neural network approach to prediction of the liquid petroleum products viscosity
title_fullStr	Neural network approach to prediction of the liquid petroleum products viscosity
title_full_unstemmed	Neural network approach to prediction of the liquid petroleum products viscosity
title_sort	neural network approach to prediction of the liquid petroleum products viscosity
publisher	Institute of Electrical and Electronics Engineers Inc.
publishDate	2021
url	https://dspace.ncfu.ru/handle/20.500.12258/14711
work_keys_str_mv	AT koldaevai neuralnetworkapproachtopredictionoftheliquidpetroleumproductsviscosity AT koldaevai neuralnetworkapproachtopredictionoftheliquidpetroleumproductsviscosity
_version_	1760602067045449728

Neural network approach to prediction of the liquid petroleum products viscosity

Նմանատիպ նյութեր